Author:
Zhang Jin,Lin Zhiting,Wu Xiulong,Peng Chunyu,Lu Wenjuan,Zhao Qiang,Chen Junning
Abstract
In-memory computing (IMC) has been widely accepted to be an effective method to improve energy efficiency. To realize IMC, operands in static random-access memory (SRAM) are stored in columns, which contradicts SRAM write patterns and requires additional data movement. In this paper, an 8T SRAM array with configurable word lines is proposed, in where the operands are arranged in rows, following the traditional SRAM storage pattern, and therefore additional data movement is not required. The proposed structure supports three different computing modes. In the ternary multiplication mode, the reference voltage generation column is not required. The energy of computing is only 1.273 fJ/bit. In the unsigned multibit multiplication mode, discharge and charging paths are used to enlarge the voltage difference of the least significant bit. In the logic operation mode, different types of operations (e.g., IMP, OR, NOR, XNOR, and XOR) are achieved in a single cycle. The frequency of logic computing is up to 909 MHz.
Subject
Electrical and Electronic Engineering,Computer Networks and Communications,Hardware and Architecture,Signal Processing,Control and Systems Engineering
Reference21 articles.
1. CONV-SRAM: An Energy-Efficient SRAM With In-Memory Dot-Product Computation for Low-Power Convolutional Neural Networks
2. XNOR-SRAM: In-Memory Computing SRAM Macro for Binary/Ternary Deep Neural Networks;Shihui;IEEE J. Solid-State Circuits,2020
Cited by
12 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献